Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
train
游雁08392f28ecfd
diff --git a/docs/tutorial/README.md b/docs/tutorial/README.mdindex 20102cca9..ef1b20884 100644--- a/docs/tutorial/README.md+++ b/docs/tutorial/README.md@@ -221,7 +221,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```diff --git a/docs/tutorial/README_zh.md b/docs/tutorial/README_zh.mdindex 4e9bb3f65..78acb5825 100644--- a/docs/tutorial/README_zh.md+++ b/docs/tutorial/README_zh.md@@ -225,7 +225,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```@@ -242,7 +242,7 @@ funasr/bin/train.py \- `train_conf.save_checkpoint_interval`(int):`5000`(默认),训练中模型保存间隔step数。- `train_conf.avg_keep_nbest_models_type`(str):`acc`(默认),保留nbest的标准为acc(越大越好)。`loss`表示,保留nbest的标准为loss(越小越好)。- `train_conf.keep_nbest_models`(int):`500`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 保留最佳的n个模型,其他删除,节约存储空间。-- `train_conf.avg_nbest_model`(int):`5`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。+- `train_conf.avg_nbest_model`(int):`10`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。- `train_conf.accum_grad`(int):`1`(默认),梯度累积功能。- `train_conf.grad_clip`(float):`10.0`(默认),梯度截断功能。- `train_conf.use_fp16`(bool):`False`(默认),开启fp16训练,加快训练速度。diff --git a/examples/README.md b/examples/README.mdindex 20102cca9..ef1b20884 100644--- a/examples/README.md+++ b/examples/README.md@@ -221,7 +221,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```diff --git a/examples/README_zh.md b/examples/README_zh.mdindex 4e9bb3f65..78acb5825 100644--- a/examples/README_zh.md+++ b/examples/README_zh.md@@ -225,7 +225,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```@@ -242,7 +242,7 @@ funasr/bin/train.py \- `train_conf.save_checkpoint_interval`(int):`5000`(默认),训练中模型保存间隔step数。- `train_conf.avg_keep_nbest_models_type`(str):`acc`(默认),保留nbest的标准为acc(越大越好)。`loss`表示,保留nbest的标准为loss(越小越好)。- `train_conf.keep_nbest_models`(int):`500`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 保留最佳的n个模型,其他删除,节约存储空间。-- `train_conf.avg_nbest_model`(int):`5`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。+- `train_conf.avg_nbest_model`(int):`10`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。- `train_conf.accum_grad`(int):`1`(默认),梯度累积功能。- `train_conf.grad_clip`(float):`10.0`(默认),梯度截断功能。- `train_conf.use_fp16`(bool):`False`(默认),开启fp16训练,加快训练速度。diff --git a/examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yaml b/examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yamlindex 150d7a007..b65a32df4 100644--- a/examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yaml+++ b/examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yaml@@ -80,7 +80,7 @@ train_conf:grad_clip: 5max_epoch: 150keep_nbest_models: 10- avg_nbest_model: 5+ avg_nbest_model: 10log_interval: 50optim: adamdiff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md b/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.mdindex 4e9bb3f65..78acb5825 100644--- a/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md@@ -225,7 +225,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```@@ -242,7 +242,7 @@ funasr/bin/train.py \- `train_conf.save_checkpoint_interval`(int):`5000`(默认),训练中模型保存间隔step数。- `train_conf.avg_keep_nbest_models_type`(str):`acc`(默认),保留nbest的标准为acc(越大越好)。`loss`表示,保留nbest的标准为loss(越小越好)。- `train_conf.keep_nbest_models`(int):`500`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 保留最佳的n个模型,其他删除,节约存储空间。-- `train_conf.avg_nbest_model`(int):`5`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。+- `train_conf.avg_nbest_model`(int):`10`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。- `train_conf.accum_grad`(int):`1`(默认),梯度累积功能。- `train_conf.grad_clip`(float):`10.0`(默认),梯度截断功能。- `train_conf.use_fp16`(bool):`False`(默认),开启fp16训练,加快训练速度。diff --git a/examples/industrial_data_pretraining/paraformer/README.md b/examples/industrial_data_pretraining/paraformer/README.mdindex 20102cca9..ef1b20884 100644--- a/examples/industrial_data_pretraining/paraformer/README.md+++ b/examples/industrial_data_pretraining/paraformer/README.md@@ -221,7 +221,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```diff --git a/examples/industrial_data_pretraining/paraformer/README_zh.md b/examples/industrial_data_pretraining/paraformer/README_zh.mdindex 4e9bb3f65..78acb5825 100644--- a/examples/industrial_data_pretraining/paraformer/README_zh.md+++ b/examples/industrial_data_pretraining/paraformer/README_zh.md@@ -225,7 +225,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```@@ -242,7 +242,7 @@ funasr/bin/train.py \- `train_conf.save_checkpoint_interval`(int):`5000`(默认),训练中模型保存间隔step数。- `train_conf.avg_keep_nbest_models_type`(str):`acc`(默认),保留nbest的标准为acc(越大越好)。`loss`表示,保留nbest的标准为loss(越小越好)。- `train_conf.keep_nbest_models`(int):`500`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 保留最佳的n个模型,其他删除,节约存储空间。-- `train_conf.avg_nbest_model`(int):`5`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。+- `train_conf.avg_nbest_model`(int):`10`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。- `train_conf.accum_grad`(int):`1`(默认),梯度累积功能。- `train_conf.grad_clip`(float):`10.0`(默认),梯度截断功能。- `train_conf.use_fp16`(bool):`False`(默认),开启fp16训练,加快训练速度。diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.shindex b4d07bd62..25d9e1a98 100644--- a/examples/industrial_data_pretraining/paraformer/finetune.sh+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh@@ -62,6 +62,6 @@ torchrun \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}\ No newline at end of filediff --git a/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md b/examples/industrial_data_pretraining/paraformer_streaming/README_zh.mdindex 4e9bb3f65..78acb5825 100644--- a/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md+++ b/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md@@ -225,7 +225,7 @@ funasr/bin/train.py \++train_conf.validate_interval=2000 \++train_conf.save_checkpoint_interval=2000 \++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=5 \+++train_conf.avg_nbest_model=10 \++optim_conf.lr=0.0002 \++output_dir="${output_dir}" &> ${log_file}```@@ -242,7 +242,7 @@ funasr/bin/train.py \- `train_conf.save_checkpoint_interval`(int):`5000`(默认),训练中模型保存间隔step数。- `train_conf.avg_keep_nbest_models_type`(str):`acc`(默认),保留nbest的标准为acc(越大越好)。`loss`表示,保留nbest的标准为loss(越小越好)。- `train_conf.keep_nbest_models`(int):`500`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 保留最佳的n个模型,其他删除,节约存储空间。-- `train_conf.avg_nbest_model`(int):`5`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。+- `train_conf.avg_nbest_model`(int):`10`(默认),保留最大多少个模型参数,配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。- `train_conf.accum_grad`(int):`1`(默认),梯度累积功能。- `train_conf.grad_clip`(float):`10.0`(默认),梯度截断功能。- `train_conf.use_fp16`(bool):`False`(默认),开启fp16训练,加快训练速度。diff --git a/funasr/models/paraformer/template.yaml b/funasr/models/paraformer/template.yamlindex 7809457df..249e88ca6 100644--- a/funasr/models/paraformer/template.yaml+++ b/funasr/models/paraformer/template.yaml@@ -87,7 +87,7 @@ train_conf:grad_clip: 5max_epoch: 150keep_nbest_models: 10- avg_nbest_model: 5+ avg_nbest_model: 10log_interval: 50optim: adamdiff --git a/funasr/models/sanm/template.yaml b/funasr/models/sanm/template.yamlindex a7f7b12d7..316fe75cb 100644--- a/funasr/models/sanm/template.yaml+++ b/funasr/models/sanm/template.yaml@@ -85,7 +85,7 @@ train_conf:- acc- maxkeep_nbest_models: 10- avg_nbest_model: 5+ avg_nbest_model: 10log_interval: 50optim: adamdiff --git a/funasr/models/scama/template.yaml b/funasr/models/scama/template.yamlindex 214046e2d..bc2e210b2 100644--- a/funasr/models/scama/template.yaml+++ b/funasr/models/scama/template.yaml@@ -91,7 +91,7 @@ train_conf:- acc- maxkeep_nbest_models: 10- avg_nbest_model: 5+ avg_nbest_model: 10log_interval: 50optim: adamdiff --git a/funasr/models/uniasr/template.yaml b/funasr/models/uniasr/template.yamlindex e72a2d527..43d55fc26 100644--- a/funasr/models/uniasr/template.yaml+++ b/funasr/models/uniasr/template.yaml@@ -171,7 +171,7 @@ train_conf:grad_clip: 5max_epoch: 150keep_nbest_models: 10- avg_nbest_model: 5+ avg_nbest_model: 10log_interval: 50optim: adamdiff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.pyindex 491e85110..27856fbb5 100644--- a/funasr/train_utils/trainer.py+++ b/funasr/train_utils/trainer.py@@ -79,7 +79,7 @@ class Trainer:self.validate_interval = kwargs.get("validate_interval", 5000)self.keep_nbest_models = kwargs.get("keep_nbest_models", 500)self.avg_keep_nbest_models_type = kwargs.get("avg_keep_nbest_models_type", "acc")- self.avg_nbest_model = kwargs.get("avg_nbest_model", 5)+ self.avg_nbest_model = kwargs.get("avg_nbest_model", 10)self.accum_grad = kwargs.get("accum_grad", 1)self.grad_clip = kwargs.get("grad_clip", 10.0)self.grad_clip_type = kwargs.get("grad_clip_type", 2.0)